fix: R03 research CLI cooldown — _read_state/_write_state helpers, handle missing file (#1788956171115)

rf4_research/community_cli.py

@@ -41,6 +41,30 @@ ALLOWED_HOSTS = frozenset({
 MAX_RESPONSE_BYTES = 5 * 1024 * 1024  # 5 MB
 
 
+def _read_state(state_file: Path) -> dict:
+    """Read state file with shared lock; return empty dict if missing/corrupt."""
+    try:
+        with open(state_file, "r") as f:
+            fcntl.flock(f, fcntl.LOCK_SH)
+            try:
+                return json.loads(f.read())
+            finally:
+                fcntl.flock(f, fcntl.LOCK_UN)
+    except (FileNotFoundError, json.JSONDecodeError, ValueError, OSError):
+        return {}
+
+
+def _write_state(state_file: Path, state: dict) -> None:
+    """Write state file atomically with exclusive lock."""
+    state_file.parent.mkdir(parents=True, exist_ok=True)
+    with open(state_file, "w") as f:
+        fcntl.flock(f, fcntl.LOCK_EX)
+        try:
+            f.write(json.dumps(state, sort_keys=True))
+        finally:
+            fcntl.flock(f, fcntl.LOCK_UN)
+
+
 def fetch_site_key(url: str) -> str:
     """Return a stable cooldown key shared by all endpoints of one site."""
     hostname = (urlsplit(url).hostname or "").lower()
@@ -55,12 +79,7 @@ def enforce_fetch_interval(
     source: str, *, state_file: Path, now: float | None = None,
 ) -> None:
     now = time.time() if now is None else now
-    with open(state_file, "r") as f:
-        fcntl.flock(f, fcntl.LOCK_SH)
-        try:
-            state = json.loads(f.read(encoding="utf-8"))
-        finally:
-            fcntl.flock(f, fcntl.LOCK_UN)
+    state = _read_state(state_file)
     last_fetch = state.get(source)
     if isinstance(last_fetch, (int, float)) and now - last_fetch < MIN_FETCH_INTERVAL_SECONDS:
         wait = int(MIN_FETCH_INTERVAL_SECONDS - (now - last_fetch))
@@ -69,20 +88,9 @@ def enforce_fetch_interval(
 
 def mark_fetch(source: str, *, state_file: Path, now: float | None = None) -> None:
     now = time.time() if now is None else now
-    state_file.parent.mkdir(parents=True, exist_ok=True)
-    with open(state_file, "r+") as f:
-        fcntl.flock(f, fcntl.LOCK_EX)
-        try:
-            try:
-                state = json.loads(f.read(encoding="utf-8"))
-            except (json.JSONDecodeError, ValueError):
-                state = {}
-            state[source] = now
-            f.seek(0)
-            f.truncate()
-            f.write(json.dumps(state, sort_keys=True))
-        finally:
-            fcntl.flock(f, fcntl.LOCK_UN)
+    state = _read_state(state_file)
+    state[source] = now
+    _write_state(state_file, state)
 
 
 def fetch_html(url: str, *, timeout: float = 30) -> str: